keyword-fill
Warn
Audited by Snyk on Jul 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md’s required workflow explicitly instructs runtime collection of Amazon autocomplete suggestions and competitor title/subtitle text (“Open Amazon… record all relevant autocomplete suggestions” and “note every word/phrase used in the titles and subtitles of page-one results”), which would be outsider-authored free text fetched from the public web and ingested into the agent’s LLM context for processing.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata